RoBERTa中文预训练模型: RoBERTa for Chinese

Aligning pretrained language models with instruction data generated by themselves.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

《Pytorch模型训练实用教程》中配套代码

FAQ-based Question Answering System

Feel free to fine tune large BERT models with Multi-GPU and FP16 support.

个人基于谷歌开源的BERT编写的文本分类器（基于微调方式），可自由加载NLP领域知名的预训练语言模型BERT、Bert-wwm、Roberta、ALBert以及ERNIE1.0

常用文本匹配模型tf版本，数据集为QA_corpus，持续更新中

CTR模型代码和学习笔记总结

BERT for Multitask Learning

中文分词 词性标注 命名实体识别 依存句法分析 成分句法分析 语义依存分析 语义角色标注 指代消解 风格转换 语义相似度 新词发现 关键词短语提取 自动摘要 文本分类聚类 拼音简繁转换 自然语言处理

LAMB Optimizer for Large Batch Training (TensorFlow version)

深度学习相关的模型训练、评估和预测相关代码

Educational material on using the TensorFlow Estimator framework for text classification

BERT for Multitask Learning

汇总各大互联网公司容易考察的高频leetcode题🔥

Easy-to-use,Modular and Extendible package of deep-learning based CTR models .

此项目是机器学习(Machine Learning)、深度学习(Deep Learning)、NLP面试中常考到的知识点和代码实现，也是作为一个算法工程师必会的理论基础知识。

LeetCode 101：力扣刷题指南

TensorFlow code and pre-trained models for BERT

ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators

XiaoMi Natural Language Processing Toolkits

Tensorflow based training and classification scripts for text, images, etc

中英文敏感词、语言检测、中外手机/电话归属地/运营商查询、名字推断性别、手机号抽取、身份证抽取、邮箱抽取、中日文人名库、中文缩写库、拆字词典、词汇情感值、停用词、反动词表、暴恐词表、繁简体转换、英文模拟中文发音、汪峰歌词生成器、职业名称词库、同义词库、反义词库、否定词库、汽车品牌词库、汽车零件词库、连续英文切割、各种中文词向量、公司名字大全、古诗词库、IT词库、财经词库、成语词库、地名词库、…

keras implement of transformers for humans

Classic papers and resources on recommendation

some attention implements

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.